scholarly journals Predicting Students’ Academic Performance: A Comparison between Traditional MLR and Machine Learning Methods with PISA 2015

2021 ◽  
Author(s):  
Shermain Puah
Keyword(s):  
Academic Performance ◽  
Educational Research ◽  
Performance Prediction ◽  
Predictive Accuracy ◽  
Lasso Regression ◽  
Machine Learning Methods ◽  
Large Numbers ◽  
Unseen Data ◽  
Research In Education ◽  
Science Performance

Predicting students’ academic performance has long been an important area of research in education. Most existing literature have made use of traditional statistical methods that run into the problems of overfitted models, inability to effectively handle large numbers of participants and predictors, and inability to pick out non-linearities that may be present. Regression-based ML methods that can produce highly interpretable yet accurate models for new predictions, are able to provide some solutions to the aforementioned problems. The present study is the first study that develops and compares between traditional MLR methods and regression-based ML methods (i.e. ridge regression, LASSO regression, elastic net, and regression trees) to predict students’ science performance in the PISA 2015. A total of 198,712 students from 60 countries, and 66 student- and school-related predictors were used to develop the predictive models. Predictive accuracy of the various models built were not that different, however, there were significant differences in the predictors identified as most important by the different methods. Although regression-based ML techniques did not outperform traditional MLR, significant advantages for using ML methods were noted and discussed. Moving forward, we strongly believe that there is merit for using such regression-based ML methods in educational research. Educational research can benefit from adopting ML practices and methods to produce models that can not only be used for explaining factors that influence academic performance prediction, but also for making more accurate predictions on unseen data.

A novel multi-stage ensemble model with multiple K-means-based selective undersampling: An application in credit scoring

2021 ◽  
Vol 40 (5) ◽  
pp. 9471-9484
Author(s):  
Yilun Jin ◽  
Yanan Liu ◽  
Wenyu Zhang ◽  
Shuai Zhang ◽  
Yu Lou
Keyword(s):  
Machine Learning ◽  
Predictive Accuracy ◽  
Credit Scoring ◽  
Imbalanced Data ◽  
Ensemble Model ◽  
Selective Sampling ◽  
Machine Learning Methods ◽  
Multi Stage ◽  
Proposed Model ◽  
New Feature

With the advancement of machine learning, credit scoring can be performed better. As one of the widely recognized machine learning methods, ensemble learning has demonstrated significant improvements in the predictive accuracy over individual machine learning models for credit scoring. This study proposes a novel multi-stage ensemble model with multiple K-means-based selective undersampling for credit scoring. First, a new multiple K-means-based undersampling method is proposed to deal with the imbalanced data. Then, a new selective sampling mechanism is proposed to select the better-performing base classifiers adaptively. Finally, a new feature-enhanced stacking method is proposed to construct an effective ensemble model by composing the shortlisted base classifiers. In the experiments, four datasets with four evaluation indicators are used to evaluate the performance of the proposed model, and the experimental results prove the superiority of the proposed model over other benchmark models.

scholarly journals Design and Optimization of a Fuzzy Logic System for Academic Performance Prediction

Symmetry ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 133
Author(s):  
Juan A. Rojas ◽  
Helbert E. Espitia ◽  
Lilian A. Bejarano
Keyword(s):  
Academic Performance ◽  
Performance Prediction ◽  
Teaching Methods ◽  
Continuous Monitoring ◽  
Educational Institution ◽  
Educational Institutions ◽  
Educational Support ◽  
Design And Optimization ◽  
Monitoring Process ◽  
Logic System

Currently, in Colombia, different problems in education exist; one of them is the inconvenience in tracing and controlling the learning trajectories that decide the topics taught in the country’s educational institutions. This work aims to implement a logic-based system that allows teachers and educational institutions to carry out a continuous monitoring process of students’ academic performance, facilitating early corrections of errors or failures in teaching methods, to promote educational support spaces within the educational institution.

Basic and Applied Research in Education: Definitions, Distinctions, and Implications

1968 ◽  
Vol 38 (2) ◽  
pp. 263-276 ◽  
Author(s):  
John Carroll
Keyword(s):  
Social Sciences ◽  
Educational Research ◽  
Applied Research ◽  
Basic Research ◽  
Research In Education ◽  
Basic And Applied Research

The author draws on the natural and social sciences to illustrate differences and interactions between applied and basic research in education. From this discussion he concludes that there is ample justification for further financial and intellectual support of the basic research component in education, and calls for a better balance in the support of basic and applied educational research.

Is it only ‘What works’ that ‘Counts’ in New Knowledge Economies? Evidence-based Practice, Educational Research and Teacher Education in Australia

2002 ◽  
Vol 1 (3) ◽  
pp. 257-266 ◽  
Author(s):  
Jill Blackmore
Keyword(s):  
Education Policy ◽  
Educational Research ◽  
Research Policy ◽  
Evidence Based ◽  
Policy And Practice ◽  
Nation States ◽  
New Knowledge ◽  
Knowledge Economies ◽  
Key Issues ◽  
Research In Education

Recent texts on globalisation and education policy refer to the rapid flow of education policy texts producing or responding to common trends across nation states with the emergence of new knowledge economies. These educational policies are shaping what counts as research and the dynamics between research, policy, and practice in schools, creating new types of relationships between universities, the public, the professions, government, and industry. The trend to evidence-based policy and practice in Australian schools is used to identify key issues within wider debates about the ‘usefulness’ of educational research and the role of universities and university-based research in education in new knowledge economies.

scholarly journals LA ÉTICA EN LA INVESTIGACIÓN EDUCATIVA

2018 ◽  
Vol 6 (1) ◽  
pp. 45-51
Author(s):  
Eddy Javier Paz Maldonado
Keyword(s):  
Educational Research ◽  
Research Process ◽  
Human Being ◽  
Ethical Problems ◽  
Fundamental Factor ◽  
Palabras Clave ◽  
Research In Education ◽  
Face Complex ◽  
International Instruments ◽  
Normative Foundations

La ética en la investigación educativa constituye un factor fundamental que debe ser considerado para la realización de estudios que incluyan la participación de diversos sujetos. Los investigadores deben enfrentarse a escenarios complejos y cumplir con una serie de pautas nacionales e internacionales que tienen como propósito respetar los derechos de las personas que se someten al proceso de investigación en el ámbito educativo. Por esta razón, existen los instrumentos internacionales y tienen como elementos primordiales los principios éticos que incluyen consideraciones sobre la persona, para impedir que sea un simple objeto estudiado. Sin embargo, en la actividad indagativa se presentan diferentes problemas éticos que están relacionados con los participantes, el incorrecto uso de la investigación, el investigador, el plagio y la utilización de datos falsos. En relación al acto ético en la investigación educativa, los educadores han de efectuar responsablemente sus estudios sin perjudicar a ningún ser humano. El objetivo de este trabajo de revisión bibliográfica, es describir la importancia de la ética en la investigación educativa.   Palabras clave: ética de la investigación, investigación educativa, principios éticos. ABSTRACT Ethics in educational research is a fundamental factor that should be considered for the realization ofstudies that include the participation of diverse subjects. Researchers must face complex scenarios andcomplete it with a series of national and international guidelines that are intended to respect the rightsof people who undergo the research process specifically in the field of education. For this reason, thereare international instruments and their main elements are ethical principles that include considerationsabout the person, to prevent it from being a simple object studied. However, in the inquiry activity thereare different ethical problems that are related to the participants, the incorrect use of the research, theresearcher, the plagiarism and the use of false data. In relation to the ethical act in educational research,educators must responsibly conduct their studies without harming any human being. The results affirmthat the ethics applied to the research in education provides to the investigators theoretical,methodological and normative foundations on the moral to achieve the development of the inquiringprocess in a coherent way. The objective of this work of bibliographical review is to describe theimportance of the ethics in educational research.

scholarly journals The Use of Critical Reading in Understanding Scientific Texts on Academic Performance and Problem-solving Skills

2020 ◽  
Vol 31 (4) ◽  
pp. 400-409
Author(s):  
Özlem Koray ◽  
◽  
Sercan Çetinkılıç ◽  
Keyword(s):  
Academic Achievement ◽  
Academic Performance ◽  
Problem Solving ◽  
Performance Level ◽  
Control Group ◽  
Critical Reading ◽  
Problem Solving Skills ◽  
Academic Level ◽  
Experimental Group ◽  
Science Performance

This study aimed to investigate the effect of critical reading (CR) practices in science courses on academic achievement, science performance level, and problem-solving skills. The experimental method and factorial design were used. The study was conducted with 102 seventh-grade students from a public school in Turkey during the 2014–2015 academic year. Experimental and control groups were formed. CR practices were followed in the experimental group and teaching practices appropriate to the curriculum were used in the control group. Data were collected with the “Multiple-Choice Academic Achievement Test” to determine the students’ academic level in the “Human and Environment Unit: The Science Performance Level Test” to determine their science performance level and the “Logical Thinking Group Test” to determine the level of their problem-solving skills. The variables of academic achievement and science performance levels were labeled “Academic Performance.” Independent samples two-way ANOVA was applied to analyze the data using SPSS 18.0 software. The results revealed that the students in the experimental group, who were taught science using CR practices, were significantly more successful than the students in the control group, whose teaching was appropriate to the current curriculum in terms of academic achievement, science performance level, and problem-solving skills. It is of critical importance to use such innovative practices, which combine various disciplines, to allow students to excel at reading, which is a basic skill, at all educational levels in order to raise contemporary and social individuals.

scholarly journals Distributing Epistemic Functions and Tasks - A Framework for Augmenting Human Analytic Power With Machine Learning in Science Education Research

2022 ◽  
Author(s):  
Marcus Kubsch ◽  
Christina Krist ◽  
Joshua Rosenberg
Keyword(s):  
Machine Learning ◽  
Science Education ◽  
Education Research ◽  
Educational Research ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Science Education Research ◽  
Computational Power ◽  
Machine Learning Methods ◽  
Applications Of Machine Learning

Machine learning has become commonplace in educational research and science education research, especially to support assessment efforts. Such applications of machine learning have shown their promise in replicating and scaling human-driven codes of students’ work. Despite this promise, we and other scholars argue that machine learning has not achieved its transformational potential. We argue that this is because our field is currently lacking frameworks for supporting creative, principled, and critical endeavors to use machine learning in science education research. To offer considerations for science education researchers’ use of ML, we present a framework, Distributing Epistemic Functions and Tasks (DEFT), that highlights the functions and tasks that pertain to generating knowledge that can be carried out by either trained researchers or machine learning algorithms. Such considerations are critical decisions that should occur alongside those about, for instance, the type of data or algorithm used. We apply this framework to two cases, one that exemplifies the cutting-edge use of machine learning in science education research and another that offers a wholly different means of using machine learning and human-driven inquiry together. We conclude with strategies for researchers to adopt machine learning and call for the field to rethink how we prepare science education researchers in an era of great advances in computational power and access to machine learning methods.

Sign in / Sign up

Export Citation Format

Share Document